Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors
Early intervention following exposure to a traumatic life event could change the clinical path from the development of post traumatic stress disorder (PTSD) to recovery, hence the interest in early detection and underlying biological mechanisms involved in the development of post traumatic sequelae....
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-09-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S105381192100519X |
| _version_ | 1818657968134029312 |
|---|---|
| author | Shelly Sheynin Lior Wolf Ziv Ben-Zion Jony Sheynin Shira Reznik Jackob Nimrod Keynan Roee Admon Arieh Shalev Talma Hendler Israel Liberzon |
| author_facet | Shelly Sheynin Lior Wolf Ziv Ben-Zion Jony Sheynin Shira Reznik Jackob Nimrod Keynan Roee Admon Arieh Shalev Talma Hendler Israel Liberzon |
| author_sort | Shelly Sheynin |
| collection | DOAJ |
| description | Early intervention following exposure to a traumatic life event could change the clinical path from the development of post traumatic stress disorder (PTSD) to recovery, hence the interest in early detection and underlying biological mechanisms involved in the development of post traumatic sequelae. We introduce a novel end-to-end neural network that employs resting-state and task-based functional MRI (fMRI) datasets, obtained one month after trauma exposure, to predict PTSD symptoms at one-, six- and fourteen-months after the exposure. FMRI data, as well as PTSD status and symptoms, were collected from adults at risk for PTSD development, after admission to emergency room following a traumatic event. Our computational method utilized a per-region encoder to extract brain regions embedding, which were subsequently updated by applying the algorithmic technique of pairwise attention. The affinities obtained between each pair of regions were combined to create a pairwise co-activation map used to perform multi-label classification. The results demonstrate that the novel method’s performance in predicting PTSD symptoms, in a prospective manner, outperforms previous analytical techniques reported in the fMRI literature, all trained on the same dataset. We further show a high predictive ability for predicting PTSD symptom clusters and PTSD persistence. To the best of our knowledge, this is the first deep learning method applied on fMRI data with respect to prospective clinical outcomes, to predict PTSD status, severity and symptom clusters. Future work could further delineate the mechanisms that underlie such a prediction, and potentially improve single patient characterization. |
| first_indexed | 2024-12-17T03:49:54Z |
| format | Article |
| id | doaj.art-1444950c08454c35b2a7baa15a5cf07f |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-12-17T03:49:54Z |
| publishDate | 2021-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-1444950c08454c35b2a7baa15a5cf07f2022-12-21T22:04:47ZengElsevierNeuroImage1095-95722021-09-01238118242Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivorsShelly Sheynin0Lior Wolf1Ziv Ben-Zion2Jony Sheynin3Shira Reznik4Jackob Nimrod Keynan5Roee Admon6Arieh Shalev7Talma Hendler8Israel Liberzon9School of Computer Science, Tel Aviv University, Tel-Aviv, IsraelCorresponding author.; School of Computer Science, Tel Aviv University, Tel-Aviv, IsraelSagol Brain Institute Tel-Aviv, Wohl Institute for Advanced Imaging, Tel Aviv Sourasky Medical Center, Tel-Aviv, Israel; Sagol School of Neuroscience, Tel-Aviv University, Tel Aviv, IsraelDepartment of Psychiatry and Behavioral Science, Texas A&M University Health Science Center, TX, USASagol Brain Institute Tel-Aviv, Wohl Institute for Advanced Imaging, Tel Aviv Sourasky Medical Center, Tel-Aviv, IsraelSagol Brain Institute Tel-Aviv, Wohl Institute for Advanced Imaging, Tel Aviv Sourasky Medical Center, Tel-Aviv, Israel; Department of Psychiatry and Behavioral Science, Stanford University School of Medicine, Stanford, USASchool of Psychological Sciences, University of Haifa, Haifa, Israel; The Integrated Brain and Behavior Research Center (IBBRC), University of Haifa, Haifa, IsraelDepartment of Psychiatry, New York University Grossman School of Medicine, New York, NY, USASagol Brain Institute Tel-Aviv, Wohl Institute for Advanced Imaging, Tel Aviv Sourasky Medical Center, Tel-Aviv, Israel; Sagol School of Neuroscience, Tel-Aviv University, Tel Aviv, Israel; School of Psychological Sciences, Faculty of Social Sciences, Tel-Aviv University, Tel-Aviv, Israel; Sackler Faculty of Medicine, Tel-Aviv University, Tel-Aviv, IsraelDepartment of Psychiatry and Behavioral Science, Texas A&M University Health Science Center, TX, USAEarly intervention following exposure to a traumatic life event could change the clinical path from the development of post traumatic stress disorder (PTSD) to recovery, hence the interest in early detection and underlying biological mechanisms involved in the development of post traumatic sequelae. We introduce a novel end-to-end neural network that employs resting-state and task-based functional MRI (fMRI) datasets, obtained one month after trauma exposure, to predict PTSD symptoms at one-, six- and fourteen-months after the exposure. FMRI data, as well as PTSD status and symptoms, were collected from adults at risk for PTSD development, after admission to emergency room following a traumatic event. Our computational method utilized a per-region encoder to extract brain regions embedding, which were subsequently updated by applying the algorithmic technique of pairwise attention. The affinities obtained between each pair of regions were combined to create a pairwise co-activation map used to perform multi-label classification. The results demonstrate that the novel method’s performance in predicting PTSD symptoms, in a prospective manner, outperforms previous analytical techniques reported in the fMRI literature, all trained on the same dataset. We further show a high predictive ability for predicting PTSD symptom clusters and PTSD persistence. To the best of our knowledge, this is the first deep learning method applied on fMRI data with respect to prospective clinical outcomes, to predict PTSD status, severity and symptom clusters. Future work could further delineate the mechanisms that underlie such a prediction, and potentially improve single patient characterization.http://www.sciencedirect.com/science/article/pii/S105381192100519XfMRIDeep learningAttention mechanismEnd-to-end neural networkPTSD symptom clusters |
| spellingShingle | Shelly Sheynin Lior Wolf Ziv Ben-Zion Jony Sheynin Shira Reznik Jackob Nimrod Keynan Roee Admon Arieh Shalev Talma Hendler Israel Liberzon Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors NeuroImage fMRI Deep learning Attention mechanism End-to-end neural network PTSD symptom clusters |
| title | Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors |
| title_full | Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors |
| title_fullStr | Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors |
| title_full_unstemmed | Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors |
| title_short | Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors |
| title_sort | deep learning model of fmri connectivity predicts ptsd symptom trajectories in recent trauma survivors |
| topic | fMRI Deep learning Attention mechanism End-to-end neural network PTSD symptom clusters |
| url | http://www.sciencedirect.com/science/article/pii/S105381192100519X |
| work_keys_str_mv | AT shellysheynin deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT liorwolf deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT zivbenzion deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT jonysheynin deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT shirareznik deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT jackobnimrodkeynan deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT roeeadmon deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT ariehshalev deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT talmahendler deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors AT israelliberzon deeplearningmodeloffmriconnectivitypredictsptsdsymptomtrajectoriesinrecenttraumasurvivors |